{"id":"W2964315724","doi":"10.48550/arxiv.1605.08988","title":"On Explore-Then-Commit Strategies","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Commit; Minimax; Mathematical optimization; Asymptotically optimal algorithm; Simple (philosophy); Gaussian; Computer science; Order (exchange); Time horizon; Empirical evidence; Horizon; Mathematical economics; Mathematics; Economics; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001337193,0.0004846768,0.0006414422,0.0009720168,0.000292552,0.0004744102,0.00387229,0.0004287937,0.001668899],"category_scores_gemma":[0.001139067,0.0003661813,0.0004068281,0.0009644918,0.0005405338,0.0008058205,0.002468818,0.001067485,0.004528654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003706044,"about_ca_system_score_gemma":0.0004690982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003387075,"about_ca_topic_score_gemma":0.00003337224,"domain_scores_codex":[0.9953985,0.0004991366,0.0004657879,0.0020297,0.0009007686,0.0007061084],"domain_scores_gemma":[0.9933577,0.002502554,0.0004367427,0.002707993,0.0006527039,0.0003423192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008831482,0.0004467542,0.00146738,0.00005413806,0.0002823452,0.002363292,0.0009365703,0.5008511,0.0001206951,0.4503167,0.01949167,0.02278621],"study_design_scores_gemma":[0.0006320141,0.0001268366,0.0006178094,0.0001044042,0.00001839104,0.000002345367,0.001600866,0.01603023,0.0002245915,0.9749893,0.005144272,0.0005089504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2549816,0.00006886682,0.7018714,0.0004193561,0.001202995,0.0005470373,0.0001356175,0.0002523762,0.04052078],"genre_scores_gemma":[0.9783825,0.0001314994,0.0001647301,0.00005836228,0.0002168514,0.00000273486,0.00000903415,0.00004089314,0.02099337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.723401,"threshold_uncertainty_score":0.999879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3686539785191696,"score_gpt":0.3317025144979235,"score_spread":0.03695146402124605,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}